© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58721
    Prev
    Next
    INDEX
    Explanations

    moving closer to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seguire
    -1.11
    ेशा
    -0.93
     Ausblick
    -0.90
    senha
    -0.87
    Away
    -0.85
     back
    -0.85
     ritorno
    -0.84
     prolonged
    -0.84
     return
    -0.83
     momentary
    -0.83
    POSITIVE LOGITS
     closer
    1.41
     with
    1.16
    closer
    1.08
     Closer
    1.07
     approached
    1.02
    Closer
    1.02
     cautiously
    1.01
     APPROACH
    0.99
     прибли
    0.99
     ближе
    0.99
    Activations Density 0.018%

    No Known Activations